Preview the prompt that would be generated

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish readOnly, idempotent, non-destructive behavior. The description adds valuable context: it is free, fully local (no network call, no credits), and shows the exact prompt that the generator would send. This goes beyond the annotations by clarifying cost and network implications.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences: first states the key benefit (free/local), second the core action, third the usage scenario. No filler, front-loaded with the most important differentiator.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose, benefit, use case, and output type (prompt and negative prompt). It does not detail the spec schema, but that is fully documented in the input schema. For a non-destructive preview tool with robust annotations, this is sufficient; the only minor omission is any note about error handling or output format details, but those are not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description only refers to 'a given spec' without elaborating on its structure. However, the input schema's nested properties contain rich descriptions for each field (name, output, etc.), so the agent can understand the spec from the schema. The description adds no new meaning to the spec parameter itself, so it relies on the schema – baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the action ('Shows the exact...prompt') and the resource (the prompt that generate_asset_reference would send), and distinguishes itself as FREE and fully local, differentiating it from the generating sibling. It names the sibling tool and clearly communicates it's a preview, not the generator.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says 'Use this to sanity-check art direction before spending image credits,' giving a clear when-to-use condition. It names generate_asset_reference as the alternative that actually spends credits, and implies this tool is for pre-flight validation. No exclusions are needed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.